{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input/igsaw-multilingual-toxic-comment-classification/jigsaw-toxic-comment-train.csv../input/jigsaw-multilingual-toxic-comment-classification/jigsaw-toxic-comment-train.csv'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = pd.read_csv(\"../input/jigsaw-multilingual-toxic-comment-classification/jigsaw-toxic-comment-train.csv\", header =0)\ndf_train","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = df_train[df_train['toxic']>0]\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import re\nfrom nltk.corpus import stopwords\nfrom nltk.stem.porter import PorterStemmer\nfrom sklearn.feature_extraction.text import CountVectorizer\n\nps = PorterStemmer()\ncorpus = stopwords.words('english')\nfor i in range(0,21384):\n    df_train['comment_text'].iloc[i] = re.sub('[^a-zA-Z]',' ',df_train['comment_text'].iloc[i])\n    df_train['comment_text'].iloc[i] = df_train['comment_text'].iloc[i].lower()\n    df_train['comment_text'].iloc[i] = df_train['comment_text'].iloc[i].split()\n    df_train['comment_text'].iloc[i] = [ps.stem(word) for word in df_train['comment_text'].iloc[i] if not word in set(corpus)]\n    df_train['comment_text'].iloc[i] = ' '.join(df_train['comment_text'].iloc[i])\n    \n\n    ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train['comment_text'].iloc[0]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train['toxicity'] = df_train['toxic']+df_train['severe_toxic']*2.0 + df_train['obscene']*1.0 +df_train['threat']*3.0+df_train['insult']*1.0+df_train['identity_hate']*2.0\ndf_train = df_train\ndf_train.describe()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cv = CountVectorizer()\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train['toxicity'] = df_train['toxic']+df_train['severe_toxic']*2.0 + df_train['obscene']*1.0 +df_train['threat']*3.0+df_train['insult']*1.0+df_train['identity_hate']*2.0\ndf_train = df_train\ndf_train.describe()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = df_train['comment_text']\nY=df_train['toxicity']\nX.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Y= np.array(Y)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.feature_extraction.text import CountVectorizer\ncv =CountVectorizer(max_features=100)\nX = cv.fit_transform(X).toarray()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train , X_test ,y_train , y_test = train_test_split(X, Y,test_size=0.2,random_state=0)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"type(y_train)\ny_train[6]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.naive_bayes import GaussianNB\nclassifier = GaussianNB()\nclassifier.fit(X_train,y_train)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred = classifier.predict(X_test)\ny_pred","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import confusion_matrix\ncm = confusion_matrix(y_test, y_pred)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(cm)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"score = pd.read_csv('../input/jigsaw-toxic-severity-rating/comments_to_score.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"score['text']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import re\nfrom nltk.corpus import stopwords\nfrom nltk.stem.porter import PorterStemmer\nfrom sklearn.feature_extraction.text import CountVectorizer\n\nps = PorterStemmer()\ncorpus = stopwords.words('english')\nfor i in range(0,7536):\n    score['text'].iloc[i] = re.sub('[^a-zA-Z]',' ',score['text'].iloc[i])\n    score['text'].iloc[i] = score['text'].iloc[i].lower()\n    score['text'].iloc[i] = score['text'].iloc[i].split()\n    score['text'].iloc[i] = [ps.stem(word) for word in score['text'].iloc[i] if not word in set(corpus)]\n    score['text'].iloc[i] = ' '.join(score['text'].iloc[i])\n    ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X1 = score['text']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X1 = cv.fit_transform(X1).toarray()\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"c1=classifier.predict(X1)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"c1","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.DataFrame()\nsub[\"comment_id\"] = score[\"comment_id\"]\nsub[\"score\"] = c1\nsub.to_csv('submission1.csv',index=False)\nsub","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"k = pd.read_csv('./submission1.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n\nk","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}